The first lever is the choice of model: using small models (Claude Haiku, Gemini Flash) for simple tasks cuts the footprint by a factor of 5 to 10 with no loss of quality. Next, switch on reasoning models only for very hard problems, and keep your prompts concise: fewer tokens, less energy. None of these habits costs anything.
Read the source article: Which AI uses the least energy? ChatGPT vs Claude vs Gemini